sglang/ GB200 perf

dsr1-fp8-1k1k-max-tpt

concurrency 2,048 · 4 days ago

cron
passed
re-run
Commit

[cookbook] Laguna-M.1: add PD disaggregation section (#28737)

Jiminator·4 days ago
PR #28737 · [cookbook] Laguna-M.1: add PD disaggregation section
Run
GitHub Actions27858605416-1
Slurm job5324
GPUs48·prefill 16 / decode 32
ISL / OSL1024 / 1024

Metrics

28 captured

best_of

1.00

burstiness

1.00

completed

20,480

duration

285

max_concurrency

2,048

mean_e2el_ms

27,378ms

mean_itl_ms

1,348ms

mean_tpot_ms

27.60ms

mean_ttft_ms

1,946ms

median_e2el_ms

26,958ms

median_itl_ms

1,381ms

median_tpot_ms

27.65ms

median_ttft_ms

1,028ms

num_prompts

20,480

output_throughput

66,222tok/s

p99_e2el_ms

37,959ms

p99_itl_ms

2,018ms

p99_tpot_ms

29.17ms

p99_ttft_ms

12,165ms

peak_output_tokens_per_s

79,719s

request_throughput

71.80tok/s

std_e2el_ms

2,996ms

std_itl_ms

253ms

std_tpot_ms

1.07ms

std_ttft_ms

2,635ms

total_input_tokens

18,880,692

total_output_tokens

18,888,974

total_token_throughput

132,414tok/s